{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T20:09:14Z","timestamp":1780603754631,"version":"3.54.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Funds for Distinguished Young Scholar","award":["62325307"],"award-info":[{"award-number":["62325307"]}]},{"name":"National Natural Science Foundation Major Scientific Research Instrument Development Project","award":["62527809"],"award-info":[{"award-number":["62527809"]}]},{"name":"Shenzhen Key Industry Research and Development Program Project","award":["ZDCY20250901102300001"],"award-info":[{"award-number":["ZDCY20250901102300001"]}]},{"name":"Guangdong Province Key Areas Research and Development Program","award":["2025B0909020002"],"award-info":[{"award-number":["2025B0909020002"]}]},{"name":"Open Project of State Key Laboratory of Synthetical Automation for Process Industries","award":["SAPI-2025-KFKT-11"],"award-info":[{"award-number":["SAPI-2025-KFKT-11"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62373257"],"award-info":[{"award-number":["62373257"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62473264"],"award-info":[{"award-number":["62473264"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62203134"],"award-info":[{"award-number":["62203134"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"crossref","award":["2023B1515120038"],"award-info":[{"award-number":["2023B1515120038"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100010877","name":"Shenzhen Science and Technology Innovation Commission","doi-asserted-by":"crossref","award":["KJZD20230923113801004"],"award-info":[{"award-number":["KJZD20230923113801004"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Intelligent Computing Center of Shenzhen University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2026.3697024","type":"journal-article","created":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T19:43:39Z","timestamp":1779824619000},"page":"10337-10349","source":"Crossref","is-referenced-by-count":0,"title":["Prioritizing Expert-Like Transitions for Reward-Free Offline Imitation Learning"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1864-9440","authenticated-orcid":false,"given":"Zhiliang","family":"Lin","sequence":"first","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0336-1181","authenticated-orcid":false,"given":"Zhuangzhuang","family":"Chen","sequence":"additional","affiliation":[{"name":"Intelligent Computing Center, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4843-2739","authenticated-orcid":false,"given":"Guanming","family":"Zhu","sequence":"additional","affiliation":[{"name":"Intelligent Computing Center, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8707-3269","authenticated-orcid":false,"given":"Li","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2208-962X","authenticated-orcid":false,"given":"Jianqiang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3352580"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3347264"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3378915"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3395626"},{"key":"ref7","first-page":"305","article-title":"ALVINN: An autonomous land vehicle in a neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"1","author":"Pomerleau"},{"key":"ref8","first-page":"2914","article-title":"Toward the fundamental limits of imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Rajaraman"},{"key":"ref9","article-title":"End to end learning for self-driving cars","author":"Bojarski","year":"2016","journal-title":"arXiv:1604.07316"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref11","first-page":"1259","article-title":"A divergence minimization perspective on imitation learning methods","volume-title":"Proc. Conf. Robot Learn.","author":"Ghasemipour"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66723-8_19"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26305"},{"key":"ref14","article-title":"Offline learning from demonstrations and unlabeled experience","author":"Zolna","year":"2020","journal-title":"arXiv:2011.13885"},{"key":"ref15","article-title":"Optimal transport for offline imitation learning","author":"Luo","year":"2023","journal-title":"arXiv:2303.13971"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2009"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230618"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2518"},{"key":"ref19","article-title":"Seabo: A simple search-based method for offline imitation learning","author":"Lyu","year":"2024","journal-title":"arXiv:2402.03807"},{"key":"ref20","first-page":"14639","article-title":"Versatile offline imitation from observations and examples via regularized state-occupancy matching","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ma"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1808"},{"key":"ref22","article-title":"Is conditional generative modeling all you need for decision-making?","author":"Ajay","year":"2022","journal-title":"arXiv:2211.15657"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref24","first-page":"21810","article-title":"MOReL: Model-based offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kidambi"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3292388"},{"key":"ref26","article-title":"Micro: Model-based offline reinforcement learning with a conservative Bellman operator","author":"Liu","year":"2024","journal-title":"arxiv:2312.03991"},{"key":"ref27","article-title":"Planning with diffusion for flexible behavior synthesis","author":"Janner","year":"2022","journal-title":"arXiv:2205.09991"},{"key":"ref28","first-page":"4933","article-title":"Offline RL without off-policy evaluation","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Brandfonbrener"},{"key":"ref29","article-title":"Offline reinforcement learning with implicit q-learning","author":"Kostrikov","year":"2021","journal-title":"arXiv:2110.06169"},{"key":"ref30","first-page":"18353","article-title":"BAIL: Best-action imitation learning for batch deep reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chen"},{"key":"ref31","article-title":"Keep doing what worked: Behavioral modelling priors for offline reinforcement learning","author":"Siegel","year":"2020","journal-title":"arXiv:2002.08396"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3403833"},{"key":"ref33","article-title":"Diffstitch: Boosting offline reinforcement learning with diffusion-based trajectory stitching","author":"Li","year":"2024","journal-title":"arXiv:2402.02439"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3486542"},{"key":"ref35","first-page":"4028","article-title":"IQ-learn: Inverse soft-Q learning for imitation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Garg"},{"key":"ref36","first-page":"10022","article-title":"Of moments and matching: A game-theoretic framework for closing the imitation gap","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Swamy"},{"key":"ref37","first-page":"158","article-title":"Implicit behavioral cloning","volume-title":"Proc. Conf. Robot Learning","author":"Florence"},{"key":"ref38","article-title":"SQIL: Imitation learning via reinforcement learning with sparse rewards","author":"Reddy","year":"2019","journal-title":"arXiv:1905.11108"},{"key":"ref39","first-page":"1","article-title":"Demodice: Offline imitation learning with supplementary imperfect demonstrations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kim"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0600"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3337230"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2956365"},{"key":"ref43","article-title":"Feedback in imitation learning: The three regimes of covariate shift","author":"Spencer","year":"2021","journal-title":"arXiv:2102.02872"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01717"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561662"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1436"},{"key":"ref47","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/361002.361007"},{"key":"ref50","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv:2011.13456"},{"key":"ref51","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv:2207.12598"},{"key":"ref52","first-page":"17842","article-title":"Diffusion models for black-box optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Krishnamoorthy"},{"key":"ref53","first-page":"5126","article-title":"Model inversion networks for model-based optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref54","article-title":"D4rl: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"key":"ref55","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fujimoto"},{"key":"ref56","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1351"},{"key":"ref59","first-page":"25611","article-title":"How to leverage unlabeled data in offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref60","article-title":"Primal Wasserstein imitation learning","author":"Dadashi","year":"2020","journal-title":"arXiv:2006.04678"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11535436.pdf?arnumber=11535436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:59:06Z","timestamp":1780603146000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11535436\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tase.2026.3697024","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}